Model comparison
DeepSeek LLM 67B vs Granite 4.0 Micro
Granite 4.0 Micro is the stronger model overall, scoring 29.0 to 24.9 on the Noometry Index.
Last verified . 3 shared benchmarks.
DeepSeekSummary
- They share 3 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Granite 4.0 Micro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Granite 4.0 Micro leads 46.7 to 31.6.
Side by side
| DeepSeek LLM 67B | Granite 4.0 Micro | |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 24.9 | 29.0 |
| Released | 2023-11-29 | 2025-10-02 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 118K |
| Input $ / M tokens | — | $0.017 |
| Output $ / M tokens | — | $0.11 |
| Results tracked | 15 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek LLM 67B: 31.9 (#278), Granite 4.0 Micro: —
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| LMArena Coding | 1096 | — |
Reasoning Granite 4.0 Micro leads
DeepSeek LLM 67B: 16.5 (#304), Granite 4.0 Micro: 19.2 (#265)
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.5 | — |
Math Granite 4.0 Micro leads
DeepSeek LLM 67B: 8.7 (#324), Granite 4.0 Micro: 12.0 (#307)
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 2.8% |
| Omni-MATH | — | 20.9% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Granite 4.0 Micro leads
DeepSeek LLM 67B: 7.0 (#313), Granite 4.0 Micro: 9.9 (#304)
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| GPQA Diamond | 24.6% | 28.3% |
| MMLU-Pro | — | 39.5% |
| GPQA (HELM) | — | 30.7% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Granite 4.0 Micro: —
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Granite 4.0 Micro leads
DeepSeek LLM 67B: 55.4 (#277), Granite 4.0 Micro: 69.9 (#169)
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| IFEval | — | 84.9% |
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Granite 4.0 Micro: —
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Granite 4.0 Micro leads
DeepSeek LLM 67B: 31.6 (#282), Granite 4.0 Micro: 46.7 (#216)
| Benchmark | DeepSeek LLM 67B | Granite 4.0 Micro |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| WildBench | — | 67% |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Granite 4.0 Micro?
Granite 4.0 Micro is the stronger model overall, scoring 29.0 to 24.9 on the Noometry Index.
How many benchmarks do DeepSeek LLM 67B and Granite 4.0 Micro share?
3 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Granite 4.0 Micro has 8.